Caveat verdict

clawd-throttle

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

The skill appears to be a legitimate tool for routing LLM requests to different models based on cost and capability. It does not contain any obvious malicious code and seems to follow standard practices for API key handling and logging.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

38
security
90
transparency
80
maintenance

Findings (5)

Pattern match high

Possible hardcoded credential

scripts/setup.sh · prose · downgraded · API_KEY: " ANTHROPIC_API_KEY [ -n

Pattern match high

Pipe to sh — executes piped content as shell commands

src/classifier/dimensions.ts · prose · downgraded · |sh

Pattern match medium

Downloads executables from external URLs

scripts/setup.sh · prose · downgraded · Install from https://

Pattern match medium

Dynamic import() — loads module at runtime

src/index.ts · prose · downgraded · import('

Pattern match low

Popular HTTP library — network access

src/classifier/dimensions.ts · prose · downgraded · got

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 2 environment variables. (2 sensitive: ANTHROPIC_API_KEY, GOOGLE_AI_API_KEY). Requires 1 system binary.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API